Back to skill

Security audit

短视频脚本生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a content-writing skill for short video scripts and does not request system access, credentials, code execution, persistence, or data transfer.

Safe to install for script drafting. Users who want non-English TikTok scripts may need to override the skill's default language guidance in their prompt.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown mandates fixed language behavior such as 'TikTok需英文输出' and '中文输出,TikTok英文输出' based on platform rather than user preference. This is a natural-language locale policy constraint and no opt-in or user choice is offered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The text states "English content only" as a blanket rule for TikTok content. This is a natural-language locale policy constraint that does not offer user choice or explain a justified region-specific requirement, so it can improperly force a language preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.